Jun 22, 2018 · Abstract:We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general ...
Jun 22, 2018 · Abstract. We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general ...
Two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general stochastic nonconvex optimization are ...
Finding local minima using Hessian matrix The most popular algorithm using. Hessian matrix to find an (,√)-approximate local minimum is the cubic regularized ...
Jun 26, 2018 · We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general stochastic ...
Finding local minima using Hessian matrix The most popular algorithm using. Hessian matrix to find an (,√)-approximate local minimum is the cubic regularized ...
Based on SNVRG, we further propose two algorithms that can find local minima faster than state-of-the-art algorithms in both finite-sum and general stochastic ( ...
Missing: via | Show results with:via
We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general stochastic nonconvex ...
We study finite-sum nonconvex optimization problems, where the objective func- tion is an average of n nonconvex functions. We propose a new stochastic ...
In this section, we review some important related works. 68. Variance reduction methods for finding stationary points. ... Stochastic nested variance reduction ...